Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0825. Min Range: -8.0825
Max Act: 8.0825. Min Act: -0.1700
Data Index: 2606326 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.8325. Min Act: -0.1700
Data Index: 4664140 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.7700. Min Act: -0.1700
Data Index: 8537165 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.7387. Min Act: -0.1700
Data Index: 3871565 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.7075. Min Act: -0.1700
Data Index: 3610604 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.6762. Min Act: -0.1700
Data Index: 3610607 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.6450. Min Act: -0.1700
Data Index: 5080223 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.6450. Min Act: -0.1700
Data Index: 1846928 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5512. Min Act: -0.1700
Data Index: 3233357 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5825. Min Act: -0.1700
Data Index: 5064991 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5825. Min Act: -0.1700
Data Index: 3424094 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5512. Min Act: -0.1700
Data Index: 6234627 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5200. Min Act: -0.1700
Data Index: 2843584 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5200. Min Act: -0.1700
Data Index: 6162345 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5200. Min Act: -0.1700
Data Index: 6960401 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.4262. Min Act: -0.1700
Data Index: 3527078 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.4262. Min Act: -0.1700
Data Index: 3020172 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.3950. Min Act: -0.1700
Data Index: 6879817 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.3637. Min Act: -0.1700
Data Index: 624193 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.4262. Min Act: -0.1700
Data Index: 8506229 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19